Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses far more than annotations provide: upsert side effects, a possible initialization warning, declarative rules replacement semantics, sticky rule ids, immutable bqName, validation failure behavior ('nothing persisted unless validation passes'), success response shape, and the fact that it does not publish or refresh BigQuery. This is exceptionally transparent for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence carries operational value, covering workflow, edge cases, and constraints. The purpose statement is front-loaded, followed by usage routing and only then detailed parameter semantics. The example concretely demonstrates the expected payload shape without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity, sparse annotations, and lack of an output schema, the description is remarkably complete. It explains prerequisites, success and warning responses, validation behavior, immutable fields, rule-id stickiness, and the scope of what the tool does and does not do. An agent has enough context to invoke it correctly in both simple and advanced scenarios.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description adds substantial parameter meaning beyond the schema: how virtualDimensionId maps to returned ids, when to omit rules, how to configure externalMetric with required discovery steps, BigQuery/S3 required fields, catalog-complete provider exceptions, and the datasource leftover echo rule. It transforms raw schema fields into actionable usage knowledge.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: it 'Upserts the virtual dimension draft for an existing virtualDimensionId' and explains both the update and seed-from-published behaviors. It explicitly distinguishes itself from create_virtual_dimension_draft, so an agent can select it correctly without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance: use create_virtual_dimension_draft only for brand-new VDIMs, and call get_skill first for allocation shapes and workflow. It also provides a concrete discovery workflow for telemetry metrics via list_metrics and states what to omit or preserve, leaving no doubt about when this tool is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.